diff --git a/litellm/__pycache__/main.cpython-311.pyc b/litellm/__pycache__/main.cpython-311.pyc
index 6841fe91c9..62fec350c1 100644
Binary files a/litellm/__pycache__/main.cpython-311.pyc and b/litellm/__pycache__/main.cpython-311.pyc differ
diff --git a/litellm/__pycache__/utils.cpython-311.pyc b/litellm/__pycache__/utils.cpython-311.pyc
index 70a03ceefe..58e8830f85 100644
Binary files a/litellm/__pycache__/utils.cpython-311.pyc and b/litellm/__pycache__/utils.cpython-311.pyc differ
diff --git a/litellm/main.py b/litellm/main.py
index d5e5fc6409..3d63f7e36b 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -93,6 +93,7 @@ def completion(
     deployment_id = None,
     # Optional liteLLM function params
     *,
+    mock_request=False, # to mock an LLM request
     return_async=False,
     api_key: Optional[str] = None,
     api_version: Optional[str] = None,
@@ -134,7 +135,13 @@ def completion(
         ):  # allow custom provider to be passed in via the model name "azure/chatgpt-test"
             custom_llm_provider = model.split("/", 1)[0]
             model = model.split("/", 1)[1]
-        
+        if mock_request == True: 
+            ## RESPONSE OBJECT
+            completion_response = "This is a mock request"
+            model_response["choices"][0]["message"]["content"] = completion_response
+            model_response["created"] = time.time()
+            model_response["model"] = "MockResponse"
+            return model_response
         # check if user passed in any of the OpenAI optional params
         optional_params = get_optional_params(
             functions=functions,
diff --git a/litellm/tests/test_mock_request.py b/litellm/tests/test_mock_request.py
new file mode 100644
index 0000000000..637aed3e7b
--- /dev/null
+++ b/litellm/tests/test_mock_request.py
@@ -0,0 +1,21 @@
+#### What this tests ####
+#    This tests mock request calls to litellm 
+
+import sys, os
+import traceback
+
+sys.path.insert(
+    0, os.path.abspath("../..")
+)  # Adds the parent directory to the system path
+import litellm
+
+def test_mock_request():
+    try:
+        model = "gpt-3.5-turbo"
+        messages = [{"role": "user", "content": "Hey, I'm a mock request"}]
+        response = litellm.completion(model=model, messages=messages, mock_request=True)
+        print(response)
+    except:
+        traceback.print_exc()
+
+test_mock_request()
\ No newline at end of file
diff --git a/litellm/utils.py b/litellm/utils.py
index d901eadfba..2a19e885b2 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -1938,8 +1938,7 @@ def exception_type(model, original_exception, custom_llm_provider):
                             llm_provider="vllm",
                             model=model
                         )
-        else:
-            raise original_exception
+        raise original_exception
     except Exception as e:
         # LOGGING
         exception_logging(
diff --git a/pyproject.toml b/pyproject.toml
index 63c955461f..0dfbbbefa5 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm"
-version = "0.1.590"
+version = "0.1.591"
 description = "Library to easily interface with LLM API providers"
 authors = ["BerriAI"]
 license = "MIT License"